Re: [Intel-gfx] [PATCH 2/7] drm/i915/guc: put all guc objects in lmem when available

[Matthew Auld <matthew.william.auld@gmail.com>]

On Wed, 1 Sept 2021 at 03:21, <John.C.Harrison@intel.com> wrote:
>
> From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
>
> The firmware binary has to be loaded from lmem and the recommendation is
> to put all other objects in there as well. Note that we don't fall back
> to system memory if the allocation in lmem fails because all objects are
> allocated during driver load and if we have issues with lmem at that point
> something is seriously wrong with the system, so no point in trying to
> handle it.
>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
> Cc: Radoslaw Szwichtenberg <radoslaw.szwichtenberg@intel.com>
> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/i915/gem/i915_gem_lmem.c  | 26 ++++++++
>  drivers/gpu/drm/i915/gem/i915_gem_lmem.h  |  4 ++
>  drivers/gpu/drm/i915/gt/uc/intel_guc.c    |  9 ++-
>  drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c | 13 ++--
>  drivers/gpu/drm/i915/gt/uc/intel_huc.c    | 14 ++++-
>  drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c  | 75 +++++++++++++++++++++--
>  6 files changed, 128 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
> index eb345305dc52..034226c5d4d0 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
> @@ -103,6 +103,32 @@ __i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915,
>                                              size, page_size, flags);
>  }
>
> +struct drm_i915_gem_object *
> +i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
> +                                     const void *data, size_t size)
> +{
> +       struct drm_i915_gem_object *obj;
> +       void *map;
> +
> +       obj = i915_gem_object_create_lmem(i915,
> +                                         round_up(size, PAGE_SIZE),
> +                                         I915_BO_ALLOC_CONTIGUOUS);

Maybe push the ALLOC_CONTIG into the caller and expose the flags
instead, assuming it's still needed for something GuC related?
pin_map() at least no longer has that constraint.